KR101970041B1 - 하이브리드 지피유/씨피유(gpu/cpu) 데이터 처리 방법 - Google Patents

하이브리드 지피유/씨피유(gpu/cpu) 데이터 처리 방법 Download PDF

Info

Publication number
KR101970041B1
KR101970041B1 KR1020157007386A KR20157007386A KR101970041B1 KR 101970041 B1 KR101970041 B1 KR 101970041B1 KR 1020157007386 A KR1020157007386 A KR 1020157007386A KR 20157007386 A KR20157007386 A KR 20157007386A KR 101970041 B1 KR101970041 B1 KR 101970041B1
Authority
KR
South Korea
Prior art keywords
search
model
gpu
partial hypothesis
hypothesis
Prior art date
Application number
KR1020157007386A
Other languages
English (en)
Korean (ko)
Other versions
KR20150065171A (ko
Inventor
이안 레인
지커 총
김중석
Original Assignee
카네기 멜론 유니버시티
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 카네기 멜론 유니버시티 filed Critical 카네기 멜론 유니버시티
Publication of KR20150065171A publication Critical patent/KR20150065171A/ko
Application granted granted Critical
Publication of KR101970041B1 publication Critical patent/KR101970041B1/ko

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L2015/081—Search algorithms, e.g. Baum-Welch or Viterbi
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Machine Translation (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Advance Control (AREA)
KR1020157007386A 2012-09-07 2013-09-09 하이브리드 지피유/씨피유(gpu/cpu) 데이터 처리 방법 KR101970041B1 (ko)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201261743607P 2012-09-07 2012-09-07
US61/743,607 2012-09-07
PCT/US2013/058829 WO2014040003A1 (en) 2012-09-07 2013-09-09 Methods for hybrid gpu/cpu data processing

Publications (2)

Publication Number Publication Date
KR20150065171A KR20150065171A (ko) 2015-06-12
KR101970041B1 true KR101970041B1 (ko) 2019-04-18

Family

ID=50237686

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020157007386A KR101970041B1 (ko) 2012-09-07 2013-09-09 하이브리드 지피유/씨피유(gpu/cpu) 데이터 처리 방법

Country Status (7)

Country Link
US (1) US9558748B2 (zh)
EP (1) EP2893435B1 (zh)
JP (1) JP6346893B2 (zh)
KR (1) KR101970041B1 (zh)
CN (1) CN104903849B (zh)
HK (1) HK1214869A1 (zh)
WO (1) WO2014040003A1 (zh)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014050981A1 (ja) * 2012-09-27 2014-04-03 日本電気株式会社 テキスト情報監視用辞書作成装置、テキスト情報監視用辞書作成方法、及び、テキスト情報監視用辞書作成プログラム
US20150234937A1 (en) * 2012-09-27 2015-08-20 Nec Corporation Information retrieval system, information retrieval method and computer-readable medium
CN103971686B (zh) * 2013-01-30 2015-06-10 腾讯科技（深圳）有限公司 自动语音识别方法和系统
CN104202209B (zh) * 2014-08-05 2017-12-22 北京遥测技术研究所 一种基于cuda的多体制信号频率快速捕获实现方法
KR102248787B1 (ko) * 2014-08-28 2021-05-06 삼성전자 주식회사 Gpu의 리소스에 대한 전력 소비 제어방법 및 장치
US10417052B2 (en) 2014-10-31 2019-09-17 Hewlett Packard Enterprise Development Lp Integrated heterogeneous processing units
JP6453631B2 (ja) * 2014-11-28 2019-01-16 株式会社東芝 認識システム、認識方法およびプログラム
US10140572B2 (en) 2015-06-25 2018-11-27 Microsoft Technology Licensing, Llc Memory bandwidth management for deep learning applications
US10002402B2 (en) 2015-07-23 2018-06-19 Sony Corporation Learning convolution neural networks on heterogeneous CPU-GPU platform
CN105577229B (zh) * 2015-12-07 2018-04-13 中国电子科技集团公司第十研究所 Cpu辅助gpu实现扩频信号快速捕获方法
US10453445B2 (en) * 2016-02-16 2019-10-22 Carnegie Mellon University System and method for multi-user GPU-accelerated speech recognition engine for client-server architectures
US11107461B2 (en) 2016-06-01 2021-08-31 Massachusetts Institute Of Technology Low-power automatic speech recognition device
US10446138B2 (en) 2017-05-23 2019-10-15 Verbit Software Ltd. System and method for assessing audio files for transcription services
KR102339716B1 (ko) * 2017-06-30 2021-12-14 삼성에스디에스 주식회사 음성 인식 방법 및 그 장치
CN109388428B (zh) * 2017-08-11 2021-05-04 华为技术有限公司 图层遍历方法、控制装置及数据处理系统
KR102699040B1 (ko) 2017-11-15 2024-08-26 삼성전자주식회사 뉴럴 네트워크 모델들의 공용 연산 그룹을 단일 처리하는 뉴럴 네트워크 시스템, 이를 포함하는 애플리케이션 프로세서 및 뉴럴 네트워크 시스템의 동작방법
US11775815B2 (en) * 2018-08-10 2023-10-03 Samsung Electronics Co., Ltd. System and method for deep memory network
JPWO2020179193A1 (zh) * 2019-03-04 2020-09-10
US11011156B2 (en) 2019-04-11 2021-05-18 International Business Machines Corporation Training data modification for training model
US11803733B2 (en) 2019-08-01 2023-10-31 Samsung Electronics Co., Ltd. Method for implementing neural network model in heterogeneous computing platform and apparatus for performing the same
CN112581582B (zh) * 2020-12-24 2024-08-16 西安翔腾微电子科技有限公司 一种基于SysML视图的GPU光栅化模块的TLM装置及操作方法
CN113360187B (zh) * 2021-04-22 2022-11-04 电子科技大学 一种基于CUDA与OpenMP的三维Kriging算法协同加速方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005091518A (ja) 2003-09-12 2005-04-07 Nippon Hoso Kyokai <Nhk> 音声認識装置及び音声認識プログラム
US20080100629A1 (en) 2003-11-19 2008-05-01 Reuven Bakalash Computing system capable of parallelizing the operation of multiple graphics processing units (GPUS) supported on a CPU/GPU fusion-type chip and/or multiple GPUS supported on an external graphics card
JP2009086202A (ja) * 2007-09-28 2009-04-23 Kddi Corp 音声認識における音響尤度並列計算装置及びそのプログラム
US20110022385A1 (en) * 2009-07-23 2011-01-27 Kddi Corporation Method and equipment of pattern recognition, its program and its recording medium
US20110202745A1 (en) 2010-02-17 2011-08-18 International Business Machines Corporation Method and apparatus for computing massive spatio-temporal correlations using a hybrid cpu-gpu approach

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62199860A (ja) 1986-02-18 1987-09-03 カイハツボ−ド株式会社 木質繊維マツト
US5477451A (en) * 1991-07-25 1995-12-19 International Business Machines Corp. Method and system for natural language translation
US5388183A (en) * 1991-09-30 1995-02-07 Kurzwell Applied Intelligence, Inc. Speech recognition providing multiple outputs
US6249761B1 (en) * 1997-09-30 2001-06-19 At&T Corp. Assigning and processing states and arcs of a speech recognition model in parallel processors
GB2409750B (en) * 2004-01-05 2006-03-15 Toshiba Res Europ Ltd Speech recognition system and technique
US7734460B2 (en) * 2005-12-20 2010-06-08 Microsoft Corporation Time asynchronous decoding for long-span trajectory model
US7877256B2 (en) * 2006-02-17 2011-01-25 Microsoft Corporation Time synchronous decoding for long-span hidden trajectory model
JP4439491B2 (ja) 2006-05-24 2010-03-24 株式会社ソニー・コンピュータエンタテインメント マルチグラフィックスプロセッサシステム、グラフィックスプロセッサおよびデータ転送方法
US8566259B2 (en) 2009-09-04 2013-10-22 The Regents Of The University Of California Method and system for parallel statistical inference on highly parallel platforms
US8484154B2 (en) * 2009-12-14 2013-07-09 Intel Corporation Methods and systems to traverse graph-based networks
US9747413B2 (en) * 2010-07-20 2017-08-29 King Abdullah University Of Science And Technology Adaptive processing for sequence alignment
US8830245B2 (en) * 2010-12-14 2014-09-09 Amazon Technologies, Inc. Load balancing between general purpose processors and graphics processors
US9240184B1 (en) * 2012-11-15 2016-01-19 Google Inc. Frame-level combination of deep neural network and gaussian mixture models

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005091518A (ja) 2003-09-12 2005-04-07 Nippon Hoso Kyokai <Nhk> 音声認識装置及び音声認識プログラム
US20080100629A1 (en) 2003-11-19 2008-05-01 Reuven Bakalash Computing system capable of parallelizing the operation of multiple graphics processing units (GPUS) supported on a CPU/GPU fusion-type chip and/or multiple GPUS supported on an external graphics card
JP2009086202A (ja) * 2007-09-28 2009-04-23 Kddi Corp 音声認識における音響尤度並列計算装置及びそのプログラム
US20110022385A1 (en) * 2009-07-23 2011-01-27 Kddi Corporation Method and equipment of pattern recognition, its program and its recording medium
US20110202745A1 (en) 2010-02-17 2011-08-18 International Business Machines Corporation Method and apparatus for computing massive spatio-temporal correlations using a hybrid cpu-gpu approach

Also Published As

Publication number Publication date
KR20150065171A (ko) 2015-06-12
CN104903849B (zh) 2017-11-28
WO2014040003A1 (en) 2014-03-13
US9558748B2 (en) 2017-01-31
JP6346893B2 (ja) 2018-06-20
CN104903849A (zh) 2015-09-09
US20150243285A1 (en) 2015-08-27
EP2893435B1 (en) 2019-05-08
EP2893435A4 (en) 2016-05-04
HK1214869A1 (zh) 2016-08-05
JP2015529350A (ja) 2015-10-05
EP2893435A1 (en) 2015-07-15

Similar Documents

Publication Publication Date Title
KR101970041B1 (ko) 하이브리드 지피유/씨피유(gpu/cpu) 데이터 처리 방법
CN107408384B (zh) 部署的端对端语音识别
US11961513B2 (en) Low-power automatic speech recognition device
US8566259B2 (en) Method and system for parallel statistical inference on highly parallel platforms
US6249761B1 (en) Assigning and processing states and arcs of a speech recognition model in parallel processors
US20160093297A1 (en) Method and apparatus for efficient, low power finite state transducer decoding
Yazdani et al. An ultra low-power hardware accelerator for automatic speech recognition
Kim et al. Efficient On-The-Fly Hypothesis Rescoring in a Hybrid GPU/CPU-based Large Vocabulary Continuous Speech Recognition Engine.
Botros et al. On efficient training of word classes and their application to recurrent neural network language models.
US9658999B2 (en) Language processing method and electronic device
JP5975938B2 (ja) 音声認識装置、音声認識方法及びプログラム
Chong et al. Efficient automatic speech recognition on the gpu
Kim et al. Accelerating large vocabulary continuous speech recognition on heterogeneous cpu-gpu platforms
Pinto et al. Design and evaluation of an ultra low-power human-quality speech recognition system
Yazdani et al. LAWS: locality-aware scheme for automatic speech recognition
You et al. Memory access optimized VLSI for 5000-word continuous speech recognition
Buthpitiya et al. A parallel implementation of viterbi training for acoustic models using graphics processing units
Liu et al. Speech recognition systems on the Cell Broadband Engine processor
Si et al. Recurrent neural network language model in mandarin voice input system
Pinto Rivero Acceleration of automatic speech recognition for low-power devices
Fukunaga et al. GPU-Based WFST Decoding with Extra Large Language Model.
Chen Cued rnnlm toolkit
Letswamotse Optimized dynamic programming search for automatic speech recognition on a Graphics Processing Unit (GPU) platform using Compute Unified Device Architecture (CUDA)
Segura Salvador Characterization of Speech Recognition Systems on GPU Architectures
Tan et al. Algorithm Optimizations: Low Computational Complexity

Legal Events

Date Code Title Description
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant